diffusers
[examples/advanced_diffusion_training] bug fixes and improvements for LoRA Dreambooth SDXL advanced training script
#5935
Merged
Overview
Commits
14
Changes
View On GitHub
Commits
  • imports and readme bug fixes
    linoytsaban committed 1 year ago
  • bug fix - ensures text_encoder params are dtype==float32 (when using pivotal tuning) even if the rest of the model is loaded in fp16
    linoytsaban committed 1 year ago
  • added pivotal tuning to readme
    linoytsaban committed 1 year ago
  • mapping token identifier to new inserted token in validation prompt (if used)
    linoytsaban committed 1 year ago
  • correct default value of --train_text_encoder_frac
    linoytsaban committed 1 year ago
  • change default value of --adam_weight_decay_text_encoder
    linoytsaban committed 1 year ago
  • validation prompt generations when using pivotal tuning bug fix
    linoytsaban committed 1 year ago
  • style fix
    linoytsaban committed 1 year ago
  • textual inversion embeddings name change
    linoytsaban committed 1 year ago
  • style fix
    linoytsaban committed 1 year ago
  • bug fix - stopping text encoder optimization halfway
    linoytsaban committed 1 year ago
  • readme - will include token abstraction and new inserted tokens when using pivotal tuning
    linoytsaban committed 1 year ago
  • Merge branch 'huggingface:main' into advanced_lora
    linoytsaban committed 1 year ago
  • style fix
    linoytsaban committed 1 year ago
FAQ Terms Privacy Refunds Impressum
Loading